Hands on - Building Intelligent Agents with LLMs

Name: Hands on - Building Intelligent Agents with LLMs
Rating: 4.3 (55 reviews)

Master LLM Agents for Advanced Reasoning, Coding Assistants, Research Assistants, and More through Hands-On Code

Created byPriyanka Dwivedi

Last updated 7/2024

English

What you'll learn

Understand the key differences between LLM prompt output, LLM Chains, Retrieval-Augmented Generation (RAG), and LLM Agents.
List and explain the main components of an LLM Agent, including tools, memory, and planning mechanisms
Utilize sophisticated task planning and reflection methods to enhance the functionality and efficiency of LLM Agents
Create and implement memory mechanisms that enable LLM Agents to sustain interaction and learn over time.
Incorporate different tools to extend and enhance the capabilities of LLM Agents.
Combine components to create complex agents such as Research Assistants, Coding Assistants, Recommendation Agents, and Agentic RAGs.
Engage in 15 interactive coding tutorials that progressively build on concepts, providing practical experience and deeper understanding.

Course content

5 sections • 48 lectures • 6h 35m total length

Introduction to the Course5:54
Introduction to Unit 11:16
Introduction to Unit 1 - Topics covered
Understanding LLMs10:03
Understand the basics of LLMs
Comparison of LLMs across benchmarks2:54
How to read the LLM comparison dashboards
LLM vs RAG vs Chain vs Agents7:23
Understand the high level difference between LLM prompting, RAG, Chains and Agents
Difference between LLM and LLM Agents3:09
What are the key differences between LLM and LLM Agents
Components of an LLM Agent9:26
The lecture explains the main components of an LLM Agent
GPT Researcher demo10:57
A quick demo of GPT Researcher framework
Setting up your API Keys2:56
Instructions on setting up your API Keys
Access code and setup your environment6:26
Steps to setup your environment
Coding your first Agent - Self Ask with Search12:01
First Agent explained and coding in Jupyter Notebook
Coding your first agent in Colab1:45
Access the First exercise in Colab
Foundation of LLM Agents - Quiz

Introduction to Tools2:44
Introduction to Unit 2
Why LLMs need tools?4:06
An explanation of why LLMs need tools
Accessing and Running tools in Langchain5:59
Details on how to use tools libraries in Langchain
Creating custom tools in Langchain7:40
Instructions and Code to create custom tools in Langchain
ReACT agent with tools14:07
Continues to build on the previous videos with tools to build a ReACT agent that can use the tools
Issues with too many tools5:40
Discusses challenges with presenting too many tools to LLMs
Recent approaches for improving tool selection8:06
Discusses couple of recent approaches to improve accuracy of tool selection
Tool Selection on RestBench dataset using OpenAI models13:26
Coding the Easy Tool selection logic on TMDB dataset using OpenAI models
Tool Selection on Rest Bench dataset using Anthropic models6:35
Coding the Easy Tool selection logic on TMDB dataset using Anthropic models
OpenAI Function Calling for tool selection12:30
OpenAI Function Calling feature
Create your own ReACT agent that "speaks" out what it sees in an input image

Introduction to Memory1:50
Introduction to the memory unit
Why do LLMs need a memory module?3:33
Explanation for why LLMs need a memory module
Different Types of Memory3:32
Different type of LLM memory modules
Understanding and Coding different short term memory modules14:24
Explanation and coding of different short term memories in Langchain
Long term memory and RAG3:01
Explanation of Retrieval Augment Generation - RAG
Coding a basic RAG pipeline10:49
This lecture goes over a basic RAG pipeline
Long Context LLMs1:44
Shows the increase in context length for LLMs
Coding a Long Context LLM9:38
Running Gemini 1.5Pro model
Comparison of RAG and Long Context LLMs
MultiModal RAG in a few lines of code6:03
How to use Embedchain to quickly build a multimodal RAG pipeline
Coding a Knowledge Agent with DB Memory - Part 19:32
Description of how to build an agent with external memory module
Coding a Knowledge Agent with DB Memory - Part 29:15
Continues on the last lecture and finishes the coding of a recommendation agent with external memory module
Unit 3 - Assignment: RAG Agent with Conversation Memory

Why do LLMs need planning?2:49
Background on LLM planning
Types of LLM Plans2:30
Discusses the two broad types of LLM planning
Chain of Thought Prompting9:59
Explanation and code for chain of thought prompting
Plan and Solve Prompting4:45
Explanation and Code for Plan and Solve Prompting
Tree of Thought Planning7:42
Explanation and Code for Tree of Thought Prompting
Skeleton of Thought Prompting6:58
Explanation and code for Skeleton of Thought Prompting
Langgraph Basics8:40
Basics of Langgraph Explained
Reflection Prompting13:38
Explanation and code for Reflection based prompting
Reflexion Prompting18:18
Explanation and Code for Researcher Reflexion Agent
Planning in LLM Agents

Agentic RAG pipeline explanation5:38
An explanation of the RAG flow enhanced with Agentic reasoning
Agentic RAG Pipeline Code18:18
Coding of the Agentic RAG flow
Movie Recommendation Bot Explanation and Tool Calls14:05
We go through the design of a movie recommendation bot
Movie Recommendation Bot - Planning and Memory16:29
Coding and testing of the movie recommendation bot
Coding Assistant - Intro4:19
Introduces the Coding Assistant and its components
Coding Assistant code walkthrough15:06
Code Walkthrough of the coding assistant

Requirements

Basic Python Programming experience
Basic understanding of Generative AI like LLMs, writing prompts etc

Description

### Course Description

Unlock the Power of Large Language Models with Our Comprehensive Course on LLM Agents!

Dive into the world of LLM Agents with our hands-on course designed to take you from basics to building sophisticated agent systems. Whether you're an AI enthusiast, a developer, or a tech professional, this course will equip you with the knowledge and skills to create powerful AI-driven agents.

What You’ll Learn:

Fundamentals of Agent Systems: Understand the core components of an agent system, including tools, memory, and planning.
Hands-On Coding: Explore each concept through interactive code notebooks, providing you with practical experience and deeper insights.
Advanced Agent Development: Build complex agents such as Research Assistants, Coding Assistants, Recommendation Agents, and Agentic RAGs, using real-world examples and scenarios.
Practical Applications: Learn how to apply these agents in various domains, enhancing productivity and innovation in your projects.

Course Highlights:

15 Interactive Code Notebooks: Each notebook is designed to break down complex concepts into manageable and understandable sections, making learning engaging and effective.
Step-by-Step Guidance: Follow along with detailed instructions and explanations, ensuring you grasp each concept before moving on.
Real-World Examples: See how these agents can be applied to solve real problems, providing you with the confidence to implement these solutions in your own work.
Community Support: Join a growing community of learners and experts, where you can share ideas, ask questions, and collaborate on projects.

By the end of this course, you’ll have a solid understanding of LLM Agents and the ability to create your own customized agents for various applications. Whether you’re looking to advance your career, start a new project, or simply satisfy your curiosity about AI, this course is your gateway to mastering LLM Agents.

Enroll now and start your journey into the future of AI with LLM Agents!

Who this course is for:

Aspiring AI specialists seeking to understand and leverage the power of LLMs
Software developers looking to innovate with Generative AI-driven applications
Data scientists aiming to broaden their expertise into AI agent design
Technologists curious about the integration of Generative AI in practical tools and services

Hands on - Building Intelligent Agents with LLMs

What you'll learn

Explore related topics

Course content

Foundation of LLM Agents12 lectures • 1hr 14min

Unit 2 - Integrating Tools with LLMs10 lectures • 1hr 21min

Unit 3 - Adding Memory to your LLM Agent11 lectures • 1hr 13min

Unit 4- Planning in LLM Agents9 lectures • 1hr 15min

Unit 5- Agent Examples6 lectures • 1hr 14min

Requirements

Description

Who this course is for: